The email announcement sent Sarah spiraling. Her stomach did a flip, a pleasant lightness spread throughout her limbs. This was a triumph, a validation of all the hours she’d poured into her writing. She felt an overwhelming surge of accomplishment; the fatigue of the long nights seemed to evaporate. She let out a whoop of joy that was so loud it startled her cat, who then scampered under the bed.

She grabbed the phone, eager to share her elation with her best friend. But then, it became apparent. The article was attributed to someone named, “Bethany Greene.” Anger flared inside her, hot and fast. Where was her name?

Her apartment suddenly felt small, suffocating. The air was too thick, the walls closing in. She slumped onto the couch, feeling as though the wind had been knocked out of her.

Emotion: jubilant

Cluster: Positive / Joy
PC1 (Valence): 3.66 Positive
PC2 (Disposition): -0.27

Role in Research

This story is one of 1,000 stories generated for the emotion jubilant. During extraction, it was fed through Gemma4-31B and its hidden state activations were captured at 11 layers.

The mean activation across all 1,000 jubilant stories, after denoising with neutral dialogue baselines, produces the jubilant emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the jubilant vector is projected through the unembedding matrix.

Promoted:
de0.738
la0.707
!0.670
ecstatic0.547
excitedly0.539
Suppressed:
S-0.768
😞-0.485
ness-0.429
😔-0.376
😥-0.351